This site takes you on a learning journey from the basics of Artificial Intelligence to the practical implementation of vector search. You’ll start with the core concepts behind Generative AI and large language models, explore the mathematics and structures that power modern AI, see how these are applied in AI search systems, and finish with a hands-on demo that brings it all together. Whether you’re new to the topic or looking to deepen your understanding, this guide connects the dots from theory to practice.
Gen AI
Learn the fundamentals of Artificial Intelligence, Machine Learning, Deep Learning, and Generative AI. Understand what large language models (LLMs) are, how they work, and how Retrieval-Augmented Generation (RAG) adds up-to-date, sourced information to AI responses.
Vectors & AI
Dive into the math and concepts that make AI search possible. Explore vectors, cosine similarity, word embeddings, and vector databases — the building blocks for representing and comparing data in AI systems.
AI Search
See how embeddings and indexes power semantic search and how techniques like Word2Vec and reranking improve relevance. Learn how these components fit into modern AI-driven retrieval pipelines.
Demo
Try it in action with a project that combines Sentence-Transformers, MongoDB Atlas Vector Search, and OpenAI’s Model Context Protocol (MCP) for intelligent semantic querying and intent routing.